Add PII redaction POC for secure LLM prompting.

Implements detect-redact-sanitize pipeline with regex, domain rules, and ONNX NER before the LLM boundary, plus NUnit tests and Xenovex push documentation. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-07 13:05:07 +05:30
commit dfc81dea28
60 changed files with 3283 additions and 0 deletions
--- a/tests/PiiRedaction.Core.Tests/Detection/RegexPiiDetectorTests.cs
+++ b/tests/PiiRedaction.Core.Tests/Detection/RegexPiiDetectorTests.cs
@@ -0,0 +1,92 @@
+using FluentAssertions;
+using PiiRedaction.Core.Detection;
+using PiiRedaction.Core.Models;
+
+namespace PiiRedaction.Core.Tests.Detection;
+
+[TestFixture]
+public sealed class RegexPiiDetectorTests
+{
+    private readonly RegexPiiDetector _detector = new();
+
+    [Test]
+    public void Detect_PositiveEmail_ReturnsEntity()
+    {
+        const string text = "Contact ravi.kumar@gmail.com now.";
+        var entities = _detector.Detect(text);
+
+        entities.Should().ContainSingle(entity =>
+            entity.Type == PiiEntityType.Email &&
+            entity.Value == "ravi.kumar@gmail.com" &&
+            entity.Source == PiiDetectionSource.Regex);
+    }
+
+    [Test]
+    public void Detect_PositivePhone_ReturnsTenDigitEntity()
+    {
+        var entities = _detector.Detect("Call 9876543210 today.");
+
+        entities.Should().ContainSingle(entity =>
+            entity.Type == PiiEntityType.Phone &&
+            entity.Value == "9876543210" &&
+            entity.Source == PiiDetectionSource.Regex);
+    }
+
+    [TestCase("Aadhaar 1234 5678 9012 linked.", "1234 5678 9012")]
+    [TestCase("Aadhaar 123456789012 linked.", "123456789012")]
+    public void Detect_PositiveAadhaar_ReturnsEntity(string text, string expectedValue)
+    {
+        var entities = _detector.Detect(text);
+
+        entities.Should().ContainSingle(entity =>
+            entity.Type == PiiEntityType.Aadhaar &&
+            entity.Value == expectedValue);
+    }
+
+    [Test]
+    public void Detect_PositivePan_ReturnsUppercaseEntity()
+    {
+        var entities = _detector.Detect("PAN ABCDE1234F verified.");
+
+        entities.Should().ContainSingle(entity => entity.Type == PiiEntityType.Pan);
+        entities[0].Value.Should().MatchRegex("^[A-Z]{5}\\d{4}[A-Z]$");
+    }
+
+    [Test]
+    public void Detect_PositiveCreditCard_ReturnsEntity()
+    {
+        var entities = _detector.Detect("Card 4111-1111-1111-1111 used.");
+
+        entities.Should().ContainSingle(entity => entity.Type == PiiEntityType.CreditCard);
+    }
+
+    [TestCase("not-an-email")]
+    [TestCase("@missing.com")]
+    [TestCase("pan abcde1234f")]
+    [TestCase("Number 987654321")]
+    public void Detect_NegativePatterns_ReturnsNoMatch(string text)
+    {
+        _detector.Detect(text).Should().BeEmpty();
+    }
+
+    [Test]
+    public void Detect_EmailSpan_HasCorrectIndices()
+    {
+        const string text = "Email ravi@test.com end.";
+        var entities = _detector.Detect(text);
+
+        var email = entities.Single(entity => entity.Type == PiiEntityType.Email);
+        email.StartIndex.Should().Be(6);
+        email.Length.Should().Be("ravi@test.com".Length);
+        text[email.StartIndex..email.EndIndex].Should().Be("ravi@test.com");
+    }
+
+    [TestCase(null)]
+    [TestCase("")]
+    [TestCase("   ")]
+    public void Detect_InvalidInput_ThrowsArgumentException(string? text)
+    {
+        var action = () => _detector.Detect(text!);
+        action.Should().Throw<ArgumentException>();
+    }
+}